Hugging Face's logo

mradermacher
/
kukulemon-spiked-9B-GGUF

Transformers
GGUF
English
mergekit
Merge
Model card Files
xet
Community
mradermacher commited on
Commit
9628c8d
·
verified ·
1 Parent(s): 38bf771

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -36,10 +36,14 @@ more details, including on how to concatenate multi-part files.
36
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q3_K_S.gguf) | Q3_K_S | 4.0 | |
37
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality |
38
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q3_K_L.gguf) | Q3_K_L | 4.8 | |
 
39
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended |
40
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended |
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q6_K.gguf) | Q6_K | 7.5 | very good quality |
42
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q8_0.gguf) | Q8_0 | 9.7 | fast, best quality |
 
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):
 
36
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q3_K_S.gguf) | Q3_K_S | 4.0 | |
37
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality |
38
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q3_K_L.gguf) | Q3_K_L | 4.8 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.IQ4_XS.gguf) | IQ4_XS | 5.0 | |
40
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q5_K_S.gguf) | Q5_K_S | 6.3 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q5_K_M.gguf) | Q5_K_M | 6.5 | |
44
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q6_K.gguf) | Q6_K | 7.5 | very good quality |
45
  | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.Q8_0.gguf) | Q8_0 | 9.7 | fast, best quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/kukulemon-spiked-9B-GGUF/resolve/main/kukulemon-spiked-9B.f16.gguf) | f16 | 18.1 | 16 bpw, overkill |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):